Novelty-based Multiobjectivization - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2011

Novelty-based Multiobjectivization

Résumé

Novelty search is a recent and promising approach to evolve neuro-controllers, especially to drive robots. The main idea is to maximize the novelty of behaviors instead of the efficiency. However, abandoning the efficiency objective(s) may be too radical in many contexts. In this paper, a Pareto- based multi-objective evolutionary algorithm is employed to reconcile novelty search with objective-based optimization by following a multiobjectivization process. Several multiobjectivizations based on behavioral novelty and on be- havioral diversity are compared on a maze navigation task. Results show that the bi-objective variant “Novelty + Fitness” is better at fine-tuning behaviors than basic novelty search, while keeping a comparable number of iterations to converge.
Fichier principal
Vignette du fichier
2011COS1944.pdf (543.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01300711 , version 1 (11-04-2016)

Identifiants

  • HAL Id : hal-01300711 , version 1

Citer

Jean-Baptiste Mouret. Novelty-based Multiobjectivization. New Horizons in Evolutionary Robotics: Extended Contributions from the 2009 EvoDeRob Workshop, Springer, pp.139-154, 2011. ⟨hal-01300711⟩
122 Consultations
1141 Téléchargements

Partager

Gmail Facebook X LinkedIn More